import time import text_utils as txu import twitter_utils as twu ''' Implementing the second feature which would produce the median for tweets in a file ft2.txt ''' # Calculate the time when the processing starts start = time.clock() # The mode of input can be a text file or twitter api json inp, outp = txu.extract_arguments() tweets = twu.get_input(inp) #initialize the median dictionary median_dict = {'median': 0.0, 'length': 0} outfile = open(outp, 'w') for tweet in tweets: median_dict = txu.get_median_iterative(tweet, median_dict) outfile.write("{0:.2f}".format(round(median_dict['median'],2))+"\n") outfile.close() # Calculate the time processing ends end = time.clock() # Print total time taken print "Total time taken in processing median: ", end - start
- extracting all URLs in the tweets - extracting all hashtags in the tweets - extracting all replyats in the tweets - get sentiment for each tweet - get worldwide trending hashtags ''' def write_csv(data, filename): with open(filename, 'wb') as csvfile: writer = csv.writer(csvfile) writer.writerows(data) if __name__ == '__main__': # get path for all outputs inp, urls, tags, replyats, sentiment, trends = txu.extract_arguments(n=7) tweets = twu.get_input(inp) tweets_text = "\n".join(tweets) # extract all URLs in the tweets and write in a file start = time.clock() txu.write_file('\n'.join(txu.get_urls(tweets_text)), urls) print "Time taken in extracting URLs: ", time.clock() - start # extract all hashtags in the tweets and write in a file start = time.clock() txu.write_file('\n'.join(txu.extract_hashtags(tweets_text)), tags) print "Time taken in extracting hashtags: ", time.clock() - start # extract all replyats in the tweets and write in a file start = time.clock()
import time import text_utils as txu import twitter_utils as twu ''' Implementing the second feature which would produce the median for tweets in a file ft2.txt ''' # Calculate the time when the processing starts start = time.clock() # The mode of input can be a text file or twitter api json inp, outp = txu.extract_arguments() tweets = twu.get_input(inp) #initialize the median dictionary median_dict = {'median': 0.0, 'length': 0} outfile = open(outp, 'w') for tweet in tweets: median_dict = txu.get_median_iterative(tweet, median_dict) outfile.write("{0:.2f}".format(round(median_dict['median'], 2)) + "\n") outfile.close() # Calculate the time processing ends end = time.clock() # Print total time taken print "Total time taken in processing median: ", end - start
- extracting all replyats in the tweets - get sentiment for each tweet - get worldwide trending hashtags ''' def write_csv(data, filename): with open(filename, 'wb') as csvfile: writer = csv.writer(csvfile) writer.writerows(data) if __name__ == '__main__': # get path for all outputs inp, urls, tags, replyats, sentiment, trends = txu.extract_arguments(n=7) tweets = twu.get_input(inp) tweets_text = "\n".join(tweets) # extract all URLs in the tweets and write in a file start = time.clock() txu.write_file('\n'.join(txu.get_urls(tweets_text)), urls) print "Time taken in extracting URLs: ", time.clock() - start # extract all hashtags in the tweets and write in a file start = time.clock() txu.write_file('\n'.join(txu.extract_hashtags(tweets_text)), tags) print "Time taken in extracting hashtags: ", time.clock() - start # extract all replyats in the tweets and write in a file start = time.clock()